Title :
CCE-based index selection for neuro assisted MR-image segmentation
Author :
Kosugi, Yukio ; Suganaimi, Yusuke ; Uemoto, Naoko ; Kameyama, Keisuke ; Sase, Mikiya ; Momose, Toshimitsu ; Nishikawa, Junichi
Author_Institution :
Tokyo Inst. of Technol., Japan
Abstract :
For image segmentation with the aid of neural networks of a reasonable size, it is important to select the most effective combination of secondary indices to be used for the classification. Here, the authors introduce a vector quantized conditional class entropy (VQCCE) criterion to evaluate which indices are effective for pattern classification, without testing on the actual classifiers. The proposed method was successfully applied for brain MR segmentation problems to classify the gray-matter/white-matter regions
Keywords :
biomedical NMR; brain; entropy; image classification; image segmentation; medical image processing; neural nets; vector quantisation; MRI; brain MR segmentation problems; gray-matter regions; magnetic resonance imaging; medical diagnostic imaging; pattern classification; secondary indices; vector quantized conditional class entropy criterion; white-matter regions; Biological neural networks; Biomedical imaging; Books; Electronic mail; Entropy; Image segmentation; Medical diagnostic imaging; Testing; Vector quantization; Virtual reality;
Conference_Titel :
Image Processing, 1996. Proceedings., International Conference on
Conference_Location :
Lausanne
Print_ISBN :
0-7803-3259-8
DOI :
10.1109/ICIP.1996.560762
